lib: code tagging framework

Add basic infrastructure to support code tagging which stores tag common
information consisting of the module name, function, file name and line
number.  Provide functions to register a new code tag type and navigate
between code tags.

Link: https://lkml.kernel.org/r/20240321163705.3067592-11-surenb@google.com
Co-developed-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Tested-by: Kees Cook <keescook@chromium.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Andreas Hindborg <a.hindborg@samsung.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: "Björn Roy Baron" <bjorn3_gh@protonmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Gary Guo <gary@garyguo.net>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 224 insertions, 0 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c63a5fbf1f1c..015fc6ee9849 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -968,6 +968,10 @@ config DEBUG_STACKOVERFLOW
 
 	  If in doubt, say "N".
 
+config CODE_TAGGING
+	bool
+	select KALLSYMS
+
 source "lib/Kconfig.kasan"
 source "lib/Kconfig.kfence"
 source "lib/Kconfig.kmsan"
diff --git a/lib/Makefile b/lib/Makefile
index ffc6b2341b45..910335da8f13 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -233,6 +233,7 @@ obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \
 	of-reconfig-notifier-error-inject.o
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 
+obj-$(CONFIG_CODE_TAGGING) += codetag.o
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
diff --git a/lib/codetag.c b/lib/codetag.c
new file mode 100644
index 000000000000..8b5b89ad508d
--- /dev/null
+++ b/lib/codetag.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/codetag.h>
+#include <linux/idr.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+#include <linux/seq_buf.h>
+#include <linux/slab.h>
+
+struct codetag_type {
+	struct list_head link;
+	unsigned int count;
+	struct idr mod_idr;
+	struct rw_semaphore mod_lock; /* protects mod_idr */
+	struct codetag_type_desc desc;
+};
+
+struct codetag_range {
+	struct codetag *start;
+	struct codetag *stop;
+};
+
+struct codetag_module {
+	struct module *mod;
+	struct codetag_range range;
+};
+
+static DEFINE_MUTEX(codetag_lock);
+static LIST_HEAD(codetag_types);
+
+void codetag_lock_module_list(struct codetag_type *cttype, bool lock)
+{
+	if (lock)
+		down_read(&cttype->mod_lock);
+	else
+		up_read(&cttype->mod_lock);
+}
+
+struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype)
+{
+	struct codetag_iterator iter = {
+		.cttype = cttype,
+		.cmod = NULL,
+		.mod_id = 0,
+		.ct = NULL,
+	};
+
+	return iter;
+}
+
+static inline struct codetag *get_first_module_ct(struct codetag_module *cmod)
+{
+	return cmod->range.start < cmod->range.stop ? cmod->range.start : NULL;
+}
+
+static inline
+struct codetag *get_next_module_ct(struct codetag_iterator *iter)
+{
+	struct codetag *res = (struct codetag *)
+			((char *)iter->ct + iter->cttype->desc.tag_size);
+
+	return res < iter->cmod->range.stop ? res : NULL;
+}
+
+struct codetag *codetag_next_ct(struct codetag_iterator *iter)
+{
+	struct codetag_type *cttype = iter->cttype;
+	struct codetag_module *cmod;
+	struct codetag *ct;
+
+	lockdep_assert_held(&cttype->mod_lock);
+
+	if (unlikely(idr_is_empty(&cttype->mod_idr)))
+		return NULL;
+
+	ct = NULL;
+	while (true) {
+		cmod = idr_find(&cttype->mod_idr, iter->mod_id);
+
+		/* If module was removed move to the next one */
+		if (!cmod)
+			cmod = idr_get_next_ul(&cttype->mod_idr,
+					       &iter->mod_id);
+
+		/* Exit if no more modules */
+		if (!cmod)
+			break;
+
+		if (cmod != iter->cmod) {
+			iter->cmod = cmod;
+			ct = get_first_module_ct(cmod);
+		} else
+			ct = get_next_module_ct(iter);
+
+		if (ct)
+			break;
+
+		iter->mod_id++;
+	}
+
+	iter->ct = ct;
+	return ct;
+}
+
+void codetag_to_text(struct seq_buf *out, struct codetag *ct)
+{
+	if (ct->modname)
+		seq_buf_printf(out, "%s:%u [%s] func:%s",
+			       ct->filename, ct->lineno,
+			       ct->modname, ct->function);
+	else
+		seq_buf_printf(out, "%s:%u func:%s",
+			       ct->filename, ct->lineno, ct->function);
+}
+
+static inline size_t range_size(const struct codetag_type *cttype,
+				const struct codetag_range *range)
+{
+	return ((char *)range->stop - (char *)range->start) /
+			cttype->desc.tag_size;
+}
+
+#ifdef CONFIG_MODULES
+static void *get_symbol(struct module *mod, const char *prefix, const char *name)
+{
+	DECLARE_SEQ_BUF(sb, KSYM_NAME_LEN);
+	const char *buf;
+
+	seq_buf_printf(&sb, "%s%s", prefix, name);
+	if (seq_buf_has_overflowed(&sb))
+		return NULL;
+
+	buf = seq_buf_str(&sb);
+	return mod ?
+		(void *)find_kallsyms_symbol_value(mod, buf) :
+		(void *)kallsyms_lookup_name(buf);
+}
+
+static struct codetag_range get_section_range(struct module *mod,
+					      const char *section)
+{
+	return (struct codetag_range) {
+		get_symbol(mod, "__start_", section),
+		get_symbol(mod, "__stop_", section),
+	};
+}
+
+static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
+{
+	struct codetag_range range;
+	struct codetag_module *cmod;
+	int err;
+
+	range = get_section_range(mod, cttype->desc.section);
+	if (!range.start || !range.stop) {
+		pr_warn("Failed to load code tags of type %s from the module %s\n",
+			cttype->desc.section,
+			mod ? mod->name : "(built-in)");
+		return -EINVAL;
+	}
+
+	/* Ignore empty ranges */
+	if (range.start == range.stop)
+		return 0;
+
+	BUG_ON(range.start > range.stop);
+
+	cmod = kmalloc(sizeof(*cmod), GFP_KERNEL);
+	if (unlikely(!cmod))
+		return -ENOMEM;
+
+	cmod->mod = mod;
+	cmod->range = range;
+
+	down_write(&cttype->mod_lock);
+	err = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL);
+	if (err >= 0)
+		cttype->count += range_size(cttype, &range);
+	up_write(&cttype->mod_lock);
+
+	if (err < 0) {
+		kfree(cmod);
+		return err;
+	}
+
+	return 0;
+}
+
+#else /* CONFIG_MODULES */
+static int codetag_module_init(struct codetag_type *cttype, struct module *mod) { return 0; }
+#endif /* CONFIG_MODULES */
+
+struct codetag_type *
+codetag_register_type(const struct codetag_type_desc *desc)
+{
+	struct codetag_type *cttype;
+	int err;
+
+	BUG_ON(desc->tag_size <= 0);
+
+	cttype = kzalloc(sizeof(*cttype), GFP_KERNEL);
+	if (unlikely(!cttype))
+		return ERR_PTR(-ENOMEM);
+
+	cttype->desc = *desc;
+	idr_init(&cttype->mod_idr);
+	init_rwsem(&cttype->mod_lock);
+
+	err = codetag_module_init(cttype, NULL);
+	if (unlikely(err)) {
+		kfree(cttype);
+		return ERR_PTR(err);
+	}
+
+	mutex_lock(&codetag_lock);
+	list_add_tail(&cttype->link, &codetag_types);
+	mutex_unlock(&codetag_lock);
+
+	return cttype;
+}